Automated analysis of confocal laser endomicroscopy images to detect head and neck cancer

Background. The purpose of this study was to develop an automated image analysis algorithm to discriminate between head and neck cancer and nonneoplastic epithelium in confocal laser endomicroscopy (CLE) images. Methods. CLE was applied to image head and neck cancer epithelium in vivo. Histopathologic diagnosis from biopsies was used to classify the CLE images offline as cancer or noncancer tissue. The classified images were used to train automated software based on distance map histograms. The performance of the final algorithm was confirmed by "leave 2 patients out" cross-validation and area under the curve (AUC)/receiver operating characteristic (ROC) analysis. Results. Ninety-two CLE videos and 92 biopsies were analyzed from 12 patients. One hundred two frames of classified neoplastic tissue and 52 frames of nonneoplastic tissue were used for cross-validation of the developed algorithm. AUC varied from 0.52 to 0.92. Conclusion. The proposed software allows an objective classification of CLE images of head and neck cancer and adjacent nonneoplastic epithelium. (C) 2015 Wiley Periodicals, Inc.